aiqbench analysis
AbGaze advances computational antibody design by introducing an attentive geometric representation learning framework that explicitly encodes cross-molecular spatial relationships rather than relying on implicit scalar distances. This approach significantly outperforms existing methods in amino-acid recovery, structural error reduction, and affinity optimization across multiple co-design tasks. The work represents a notable step forward in applying specialized machine learning architectures to solve complex protein engineering challenges.
AbGaze: Attentive Geometric Representation Learning for End-to-End Antibody Design
arXiv:2609.35296v1 Announce Type: new Abstract: Computational antibody design requires representations that capture the geometric patterns underlying antigen--antibody interactions, yet existing approaches often rely on scalar distances or surface-intrinsic features, leaving cross-molecular geometry largely implicit. We present AbGaze, an end-to-end antibody design framework based on attentive geometric representation learning, which encodes distance, spatial direction, and surface-normal orientation of antigen surfaces relative to antibody-residue local frames, and adaptively aggregates these geometric interactions according to their interfacial context. The learned interaction representation is shared across multi-CDR co-design, complex structure prediction, and affinity optimization, with local-frame geometric supervision further constraining the representation. AbGaze outperforms prior methods across all three tasks: relative to the second-best method, it improves amino-acid recovery by 7.1% and reduces structural error by 14.9% on average over the six CDRs, improves interface docking quality (DockQ) by 6.6%, and raises the affinity improvement rate (IMP) by 32.5%.
Abstract:Computational antibody design requires representations that capture the geometric patterns underlying antigen--antibody interactions, yet existing approaches often rely on scalar distances or surface-intrinsic features, leaving cross-molecular geometry largely implicit. We present AbGaze, an end-to-end antibody design framework based on attentive geometric representation learning, which encodes distance, spatial direction, and surface-normal orientation of antigen surfaces relative to antibody-residue local frames, and adaptively aggregates these geometric interactions according to their interfacial context. The learned interaction representation is shared across multi-CDR co-design, complex structure prediction, and affinity optimization, with local-frame geometric supervision further constraining the representation. AbGaze outperforms prior methods across all three tasks: relative to the second-best method, it improves amino-acid recovery by 7.1% and reduces structural error by 14.9% on average over the six CDRs, improves interface docking quality (DockQ) by 6.6%, and raises the affinity improvement rate (IMP) by 32.5%.
Artificial Intelligence (cs.AI)
arXiv:2609.35296 [cs.AI]
(or arXiv:2609.35296v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.35296 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 234 words
Related coverage
EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning
arXiv · Jun 5, 2026
ArGEnT: Arbitrary Geometry-encoded Transformer for Operator Learning
arXiv · Aug 17, 2026
Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers
arXiv · Jun 17, 2026
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
arXiv · Jul 23, 2026